Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?"
.claude/skills/reinamaccredy-gitnexus-guide/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -30% | 0% |
Quick reference for all GitNexus MCP tools, resources, and the knowledge graph schema.
For any task involving code understanding, debugging, impact analysis, or refactoring:
gitnexus://repo/{name}/context — codebase overview + check index freshness> If step 1 warns the index is stale, run npx gitnexus analyze in the terminal first.
| Task | Skill to read | | -------------------------------------------- | ------------------- | | Understand architecture / "How does X work?" | gitnexus-exploring | | Blast radius / "What breaks if I change X?" | gitnexus-impact-analysis | | Trace bugs / "Why is X failing?" | gitnexus-debugging | | Rename / extract / split / refactor | gitnexus-refactoring | | Tools, resources, schema reference | gitnexus-guide (this file) | | Index, status, clean, wiki CLI commands | gitnexus-cli |
| Tool | What it gives you | | ---------------- | ------------------------------------------------------------------------ | | query | Process-grouped code intelligence — execution flows related to a concept | | context | 360-degree symbol view — categorized refs, processes it participates in | | impact | Symbol blast radius — what breaks at depth 1/2/3 with confidence | | detect_changes | Git-diff impact — what do your current changes affect | | rename | Multi-file coordinated rename with confidence-tagged edits | | cypher | Raw graph queries (read gitnexus://repo/{name}/schema first) | | list_repos | Discover indexed repos |
Lightweight reads (~100-500 tokens) for navigation:
| Resource | Content | | ---------------------------------------------- | ----------------------------------------- | | gitnexus://repo/{name}/context | Stats, staleness check | | gitnexus://repo/{name}/clusters | All functional areas with cohesion scores | | gitnexus://repo/{name}/cluster/{clusterName} | Area members | | gitnexus://repo/{name}/processes | All execution flows | | gitnexus://repo/{name}/process/{processName} | Step-by-step trace | | gitnexus://repo/{name}/schema | Graph schema for Cypher |
Nodes: File, Function, Class, Interface, Method, Community, Process Edges (via CodeRelation.type): CALLS, IMPORTS, EXTENDS, IMPLEMENTS, DEFINES, MEMBER_OF, STEP_IN_PROCESS
cypherMATCH (caller)-[:CodeRelation {type: 'CALLS'}]->(f:Function {name: "myFunc"}) RETURN caller.name, caller.filePath
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,989 | 4,725 | -61% | 1 | 1 | 0% | 1,848 | 1,456 | -21% | 0 | 0 | — |
case-02 | fail→pass | 12,649 | 5,134 | -59% | 1 | 1 | 0% | 1,894 | 1,638 | -14% | 0 | 0 | — |
case-03 | fail→pass | 14,119 | 9,396 | -33% | 1 | 1 | 0% | 1,899 | 2,068 | +9% | 0 | 0 | — |
case-04 | pass→pass | 8,548 | 1,813 | -79% | 1 | 1 | 0% | 1,280 | 950 | -26% | 0 | 0 | — |
case-05 | fail→pass | 6,862 | 2,299 | -66% | 1 | 1 | 0% | 1,086 | 1,091 | +0% | 0 | 0 | — |
case-06 | fail→pass | 10,835 | 2,490 | -77% | 1 | 1 | 0% | 1,644 | 1,147 | -30% | 0 | 0 | — |
case-07 | fail→pass | 18,728 | 2,085 | -89% | 1 | 1 | 0% | 1,893 | 1,120 | -41% | 0 | 0 | — |
case-08 | fail→pass | 9,572 | 2,089 | -78% | 1 | 1 | 0% | 1,724 | 1,036 | -40% | 0 | 0 | — |
case-09 | fail→pass | 16,157 | 2,314 | -86% | 1 | 1 | 0% | 2,573 | 1,098 | -57% | 0 | 0 | — |
case-10 | pass→pass | 7,320 | 1,421 | -81% | 1 | 1 | 0% | 1,198 | 928 | -23% | 0 | 0 | — |
case-11 | pass→pass | 22,568 | 1,900 | -92% | 1 | 1 | 0% | 3,962 | 985 | -75% | 0 | 0 | — |
case-12 | fail→pass | 5,067 | 1,953 | -61% | 1 | 1 | 0% | 878 | 1,008 | +15% | 0 | 0 | — |
case-17 | fail→pass | 7,474 | 1,699 | -77% | 1 | 1 | 0% | 1,360 | 1,052 | -23% | 0 | 0 | — |
case-13 | pass→pass | 4,159 | 1,962 | -53% | 1 | 1 | 0% | 571 | 991 | +74% | 0 | 0 | — |
case-14 | fail→pass | 6,627 | 1,690 | -74% | 1 | 1 | 0% | 1,226 | 1,005 | -18% | 0 | 0 | — |
case-15 | fail→pass | 6,971 | 2,420 | -65% | 1 | 1 | 0% | 1,194 | 1,141 | -4% | 0 | 0 | — |
case-16 | fail→pass | 13,865 | 3,199 | -77% | 1 | 1 | 0% | 2,231 | 969 | -57% | 0 | 0 | — |
case-18 | pass→pass | 11,100 | 2,280 | -79% | 1 | 1 | 0% | 2,088 | 1,132 | -46% | 0 | 0 | — |
case-19 | fail→pass | 10,790 | 1,982 | -82% | 1 | 1 | 0% | 1,822 | 1,046 | -43% | 0 | 0 | — |
case-20 | fail→pass | 8,405 | 4,994 | -41% | 1 | 1 | 0% | 1,524 | 1,318 | -14% | 0 | 0 | — |
case-21 | pass→pass | 9,986 | 5,198 | -48% | 1 | 1 | 0% | 1,805 | 1,605 | -11% | 0 | 0 | — |
case-22 | fail→fail | 15,475 | 2,785 | -82% | 1 | 1 | 0% | 3,275 | 936 | -71% | 0 | 0 | — |
case-23 | fail→fail | 10,600 | 5,822 | -45% | 1 | 1 | 0% | 1,931 | 1,781 | -8% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 22 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +65 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.